Question 11.16

11.16 The statistics of writing style. Numerical data can distinguish different types of writing, and sometimes even individual authors. Here are data collected by students on the percentages of words of 1 to 15 letters used in articles in Popular Science magazine:

Length: 1 2 3 4 5
Percent: 3.6 14.8 18.7 16.0 12.5
Length: 6 7 8 9 10
Percent: 8.2 8.1 5.9 4.4 3.6
Length: 11 12 13 14 15
Percent: 2.1 0.9 0.6 0.4 0.2
  1. (a) Make a histogram of this distribution. Describe its shape, center, and variability.

  2. (b) How does the distribution of lengths of words used in Popular Science compare with the similar distribution in Figure 11.4 (page 254) for Shakespeare’s plays? Look in particular at short words (two, three, and four letters) and very long words (more than 10 letters).